CN117825957A - Fault detection method of power battery - Google Patents
Fault detection method of power battery Download PDFInfo
- Publication number
- CN117825957A CN117825957A CN202311630565.3A CN202311630565A CN117825957A CN 117825957 A CN117825957 A CN 117825957A CN 202311630565 A CN202311630565 A CN 202311630565A CN 117825957 A CN117825957 A CN 117825957A
- Authority
- CN
- China
- Prior art keywords
- power battery
- real
- time
- data
- fault detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 42
- 239000000178 monomer Substances 0.000 claims abstract description 33
- 238000010801 machine learning Methods 0.000 claims abstract description 10
- 238000012216 screening Methods 0.000 claims abstract description 7
- 238000013528 artificial neural network Methods 0.000 claims description 18
- 239000000523 sample Substances 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 2
- 238000011897 real-time detection Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 8
- 239000006185 dispersion Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Operations Research (AREA)
- Biomedical Technology (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Secondary Cells (AREA)
Abstract
The invention relates to a fault detection method of a power battery, and belongs to the field of safety evaluation of battery systems. The method comprises the following steps: s1: collecting power battery data of normal operation of an electric automobile, including operation data of each monomer in a power battery pack, and establishing a power battery database; s2: according to the collected battery data, screening out characteristics related to the single voltage by using a correlation coefficient method; s3: based on the features extracted in the step S2, a real-time fault detection model of the power battery is established by using a machine learning algorithm; s4: inputting real-time power battery data of the electric automobile into the trained model in the step S3, and if the real-time single voltage exceeds the confidence interval output by the model in the step S3, indicating that a fault occurs; if the real-time single voltage is within the confidence interval output by the model in the S3, the battery is indicated to be normal. The invention can effectively realize the real-time detection of the faults of the power battery of the electric automobile and accurately position the faulty single body.
Description
Technical Field
The invention belongs to the field of safety evaluation of battery systems, and relates to a fault detection method of a power battery.
Background
With the rapid development of the electric automobile industry, the safety performance of the power battery becomes a focus of social attention. The power battery is one of the most central and key components of the electric automobile, and the safety of the power battery is directly related to the use safety of the electric automobile. Therefore, the safety state of the power battery is monitored in real time, and whether faults occur or not is detected, so that the safety state is a key for ensuring the safe and reliable operation of the electric automobile.
However, most of the existing fault detection technologies are developed based on batteries under laboratory conditions, and are not applicable to power batteries under complex and variable actual running conditions of electric vehicles.
Disclosure of Invention
Accordingly, the present invention is directed to a method for detecting a failure of a power battery, which can detect a failure of a power battery in real time and is suitable for a real-vehicle condition.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the fault detection method of the power battery specifically comprises the following steps:
s1: collecting power battery data of normal operation of the electric automobile, including operation data of each monomer in a power battery pack, and establishing a power battery database;
s2: according to the collected battery data, screening out characteristics related to the single voltage by using a correlation coefficient method;
s3: based on the features extracted in the step S2, an advanced machine learning algorithm is utilized to establish a real-time fault detection model of the power battery;
s4: inputting real-time power battery data of the electric automobile into the real-time fault detection model trained in the step S3, and if the real-time single voltage exceeds the confidence interval output by the model in the step S3, indicating that a fault occurs; if the real-time cell voltage is within the confidence interval output by the model in step S3, it is indicated that the battery is operating normally.
Further, the step S1 specifically includes the following steps:
s11: collecting power battery data of normal operation of an electric automobile, wherein the data comprise battery parameters such as time, current, voltage, temperature and the like;
s12: collecting monomer operation data of the power battery, including monomer voltages of all monomers in a power battery pack and temperatures of all temperature probes placed near the monomers;
s13: and establishing a power battery database according to the collected battery data.
Further, the step S2 specifically includes the following steps:
s21: data theoretically related to the single voltage is primarily screened out from a power battery database to be used as a characteristic;
the data theoretically related to the cell voltage includes total current, cell pack voltage, average cell voltage, SOC, cell pack temperature, internal resistance, SOH, discharge rate, etc.;
s22: screening out the characteristics with high correlation with the monomer voltage from the characteristics selected in the step S21 by using a correlation coefficient method;
the correlation coefficient method is a pearson correlation coefficient method, a gray scale correlation coefficient method and the like, and the characteristic of high correlation is a characteristic that the correlation coefficient is larger than 0.75, 0.8 or 0.85.
Further, the step S3 specifically includes:
s31: selecting a probability regression algorithm as a target machine learning algorithm;
s32: based on the screened characteristics and the single voltage data, a probability regression algorithm is utilized to establish a real-time fault detection model
The machine learning algorithm adopts a probability regression algorithm, wherein the probability regression algorithm is a probability neural network, gaussian process regression or correlation vector machine regression and is used for realizing probability prediction.
Further, the step S4 specifically includes the following steps:
s41: inputting real-time battery operation data by using a trained real-time fault detection model, and judging whether faults occur or not by judging whether the real-time single voltage exceeds a confidence interval output by the real-time fault detection model; if the confidence interval is exceeded, indicating that the fault occurs; otherwise, it indicates that there is no fault;
s42: if the fault occurs, the fault monomer can be positioned according to the voltage of the fault monomer.
Further, in step S4, the confidence interval is a 95% confidence interval output by using gaussian process regression or probabilistic neural network, and the expression is as follows:
wherein,mean value representing gaussian process regression or probabilistic neural network output, +.>Representing gaussian process regression or probabilityVariance of the output of the rate neural network.
The invention has the beneficial effects that: the invention can effectively realize the real-time detection of the faults of the power battery of the electric automobile and accurately position the faulty single body.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objects and other advantages of the invention may be realized and obtained by means of the instrumentalities and combinations particularly pointed out in the specification.
Drawings
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in the following preferred detail with reference to the accompanying drawings, in which:
FIG. 1 is an overall flow chart of a method of detecting a failure of a power cell of the present invention;
FIG. 2 is a plot of the monomer voltage for normal and faulty monomers in example 1 or example 2;
fig. 3 is a failure detection result of the normal monomer and the failure monomer in example 1.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the illustrations provided in the following embodiments merely illustrate the basic idea of the present invention by way of illustration, and the following embodiments and features in the embodiments may be combined with each other without conflict.
Wherein the drawings are for illustrative purposes only and are shown in schematic, non-physical, and not intended to limit the invention; for the purpose of better illustrating embodiments of the invention, certain elements of the drawings may be omitted, enlarged or reduced and do not represent the size of the actual product; it will be appreciated by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numbers in the drawings of embodiments of the invention correspond to the same or similar components; in the description of the present invention, it should be understood that, if there are terms such as "upper", "lower", "left", "right", "front", "rear", etc., that indicate an azimuth or a positional relationship based on the azimuth or the positional relationship shown in the drawings, it is only for convenience of describing the present invention and simplifying the description, but not for indicating or suggesting that the referred device or element must have a specific azimuth, be constructed and operated in a specific azimuth, so that the terms describing the positional relationship in the drawings are merely for exemplary illustration and should not be construed as limiting the present invention, and that the specific meaning of the above terms may be understood by those of ordinary skill in the art according to the specific circumstances.
Referring to fig. 1 to 3, the present invention provides a fault detection method for a power battery, which specifically includes the following steps:
s1: collecting power battery data of normal operation of an electric automobile, including operation data of each monomer in a power battery pack, and establishing a power battery database, wherein the method specifically comprises the following steps:
s11: collecting the running data of a complete power battery of an electric automobile, wherein the running data comprise battery parameters such as time, current, voltage, temperature and the like;
s12: collecting monomer operation data of the power battery, including monomer voltages of all monomers in a power battery pack and temperatures of all temperature probes placed near the monomers;
s13: and establishing a power battery database according to the collected battery data.
S2: according to the collected battery data, the characteristics related to the cell voltage are screened out by using a correlation coefficient method, and the method specifically comprises the following steps:
s21: primarily screening data theoretically related to the monomer voltage as characteristics;
the data related to the cell voltage theoretically includes total current, cell pack voltage, average cell voltage, SOC, cell pack temperature, internal resistance, SOH, discharge rate, etc.
S22: and screening out the characteristics with high correlation with the monomer voltage by using a correlation coefficient method.
The correlation coefficient method can adopt a pearson correlation coefficient, and the formula is as follows:
features with high cell voltage correlation may be selected as high correlation features with pearson correlation coefficients greater than 0.8.
S3: based on the features extracted in the step S2, an advanced machine learning algorithm is utilized to build a real-time fault detection model of the power battery, and the method specifically comprises the following steps:
s31: selecting a probability regression algorithm as a target machine learning algorithm;
s32: based on the screened characteristics and the single voltage data, a probability regression algorithm is utilized to establish a real-time fault detection model.
S4: inputting real-time power battery data of the electric automobile into the trained model in the step S3, and if the real-time single voltage exceeds the confidence interval output by the model in the step S3, indicating that a fault occurs; if the real-time cell voltage is within the confidence interval output by the model in step S3, it is indicated that the battery is operating normally. The method specifically comprises the following steps:
s41: inputting real-time battery operation data by using the trained real-time fault detection model, and judging whether faults occur or not by judging whether the real-time single voltage exceeds a confidence interval output by the real-time fault detection model; if the confidence interval is exceeded, indicating that the fault occurs; otherwise, it indicates that there is no fault;
s42: if the fault occurs, the fault monomer can be positioned according to the voltage of the fault monomer.
Example 1:
the probability regression algorithm selected in step S31 may adopt a gaussian process regression, and the gaussian process regression algorithm flow is as follows:
the gaussian process is generally determined by a mean function m (x) and a kernel function k (x, x'), and can be expressed as:
f(x)＝GP(m(x),k(x,x′))
typically, 0 is chosen as the mean function of the gaussian process (m (x) =0), and the SE kernel function is chosen as the kernel function of the gaussian process. The expression of the SE kernel function is:
where Θ represents a length parameter. Considering the complex operating environment of an electric car, the prior distribution obtained by gaussian process regression can be expressed as:
y(x)＝f(x)+ε
where ε is white noise that fits a Gaussian distribution. For a given input d= (X, y), the posterior distribution of gaussian process regression outputs can be expressed as:
wherein I is n Is an n-dimensional identity matrix.
The confidence interval in step S41 may be a 95% confidence interval output by gaussian process regression, which is expressed as follows:
wherein,mean value of regression output of Gaussian process, +.>Representing the variance of the regression output of the gaussian process.
Example 2:
the probability regression algorithm selected in step S31 may employ a probability neural network, and the probability neural network flow is as follows:
the theoretical basis of the probabilistic neural network is a bayesian minimum risk criterion, namely bayesian decision theory. The probabilistic neural network is typically connected to a fully connected neural network, providing a probability distribution to the output of the fully connected neural network by setting weights and variances.
One fully connected neural network with input x, weight ω and output y can be expressed as
y＝f(x,ω)+ε
Where ε is noise that obeys a certain distribution and is used to represent the uncertainty that the model cannot capture. When the prior distribution P (ω) incorporating the weight parameter ω is obtained, the posterior distribution can be expressed as the product of the prior distribution and the likelihood function divided by the edge likelihood based on the bayesian theorem:
P(ω|y)＝P(y|ω)*P(ω)/P(y)
where P (ω|y) is a likelihood function representing the probability of observing the data y given the weight ω. P (y) is the edge likelihood.
Since it is difficult to directly calculate the posterior distribution, a variation distribution Q (ω) is typically introduced to approximate the true posterior distribution P (ω|y). Q (ω) and P (ω|y) are made as close as possible by minimizing the variation dispersion (KL dispersion):
once the approximate posterior distribution Q (ω) is obtained, the standard deviation or confidence interval of the predicted value can be calculated.
The confidence interval in step S41 may be a 95% confidence interval output by the probabilistic neural network, which is expressed as follows:
wherein,mean value of output of the probability neural network, +.>Representing the variance of the probabilistic neural network output.
Verification experiment:
to illustrate the effectiveness of the present invention, example 1 or example 2 of the present invention prepares operational data of a failed vehicle in which a battery cell fails to be alerted by the BMS. Fig. 2 shows the voltage of a faulty cell and the voltage of a normal cell of a faulty vehicle battery. Through testing, by using the machine learning algorithm of the embodiment 1 of the present invention, compared with the BMS, 1783s detects the fault in advance, and there is no false alarm for the normal monomer, and the detection result is shown in fig. 3. Compared with the BMS, the machine learning algorithm of the embodiment 2 of the invention detects faults 1754 seconds in advance, and has no false alarm for normal monomers. Therefore, fault monomer positioning is realized while real-time fault detection is realized.
Finally, it is noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made thereto without departing from the spirit and scope of the present invention, which is intended to be covered by the claims of the present invention.
Claims (6)
1. The fault detection method of the power battery is characterized by comprising the following steps of:
s1: collecting power battery data of normal operation of the electric automobile, including operation data of each monomer in a power battery pack, and establishing a power battery database;
s2: according to the collected battery data, screening out characteristics related to the single voltage by using a correlation coefficient method;
s3: based on the features extracted in the step S2, a real-time fault detection model of the power battery is established by using a machine learning algorithm;
s4: inputting real-time power battery data of the electric automobile into the real-time fault detection model trained in the step S3, and if the real-time single voltage exceeds the confidence interval output by the model in the step S3, indicating that a fault occurs; if the real-time cell voltage is within the confidence interval output by the model in step S3, it is indicated that the battery is operating normally.
2. The method for detecting the failure of the power battery according to claim 1, wherein the step S1 specifically includes the steps of:
s11: collecting power battery data of normal operation of an electric automobile, wherein the data comprise time, current, voltage and temperature;
s12: collecting monomer operation data of the power battery, including monomer voltages of all monomers in a power battery pack and temperatures of all temperature probes placed near the monomers;
s13: and establishing a power battery database according to the collected battery data.
3. The fault detection method of a power battery according to claim 1, wherein the step S2 specifically includes the steps of:
s21: data theoretically related to the single voltage is primarily screened out from a power battery database to be used as a characteristic;
the data theoretically related to the cell voltage comprises total current, cell pack voltage, average cell voltage, SOC, cell pack temperature, internal resistance, SOH and discharge multiplying power;
s22: screening out the characteristics with high correlation with the monomer voltage from the characteristics selected in the step S21 by using a correlation coefficient method;
the correlation coefficient method is a pearson correlation coefficient method or a gray scale correlation coefficient method, and the characteristic of high correlation is a characteristic that the correlation coefficient is larger than 0.75, 0.8 or 0.85.
4. The method for detecting a fault of a power battery according to claim 1, wherein in step S3, the machine learning algorithm is a probabilistic regression algorithm, and the probabilistic regression algorithm is a probabilistic neural network, gaussian process regression or correlation vector machine regression, and is used for implementing probability prediction.
5. The fault detection method of a power battery according to claim 1, wherein the step S4 specifically includes the steps of:
s41: inputting real-time battery operation data by using a trained real-time fault detection model, and judging whether faults occur or not by judging whether the real-time single voltage exceeds a confidence interval output by the real-time fault detection model; if the confidence interval is exceeded, indicating that the fault occurs; otherwise, it indicates that there is no fault;
s42: if the fault occurs, positioning the faulty monomer according to the voltage of the faulty monomer.
6. The method according to claim 1, wherein in step S4, the confidence interval is a 95% confidence interval output by using gaussian process regression or probabilistic neural network, and the expression is as follows:
wherein,mean value representing gaussian process regression or probabilistic neural network output, +.>Representing the variance of the gaussian process regression or probabilistic neural network output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311630565.3A CN117825957A (en) | 2023-11-30 | 2023-11-30 | Fault detection method of power battery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311630565.3A CN117825957A (en) | 2023-11-30 | 2023-11-30 | Fault detection method of power battery |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117825957A true CN117825957A (en) | 2024-04-05 |
Family
ID=90508604
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311630565.3A Pending CN117825957A (en) | 2023-11-30 | 2023-11-30 | Fault detection method of power battery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117825957A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112986839A (en) * | 2021-02-25 | 2021-06-18 | 北京理工大学 | Confidence interval-based fault diagnosis method and system for lithium ion power battery pack |
| CN113459867A (en) * | 2021-07-19 | 2021-10-01 | 青岛科技大学 | Electric vehicle charging process fault early warning method based on adaptive deep confidence network |
| CN115327386A (en) * | 2022-08-09 | 2022-11-11 | 重庆大学 | Battery pack multi-fault diagnosis method based on electric-thermal coupling model |
| CN115792680A (en) * | 2022-12-26 | 2023-03-14 | 中山大学·深圳 | Retired battery health state assessment method based on Bayes deep learning |
| CN116482536A (en) * | 2023-01-30 | 2023-07-25 | 吉林大学 | Power battery fault early warning and safety risk assessment method based on data driving |
| CN116901707A (en) * | 2023-06-14 | 2023-10-20 | 浙江吉利控股集团有限公司 | Power battery pack fault early warning method, system and vehicle |
| CN117054887A (en) * | 2023-08-17 | 2023-11-14 | 摩形新能源汽车咨询集团(澄迈)有限公司 | Internal fault diagnosis method for lithium ion battery system |
-
2023
- 2023-11-30 CN CN202311630565.3A patent/CN117825957A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112986839A (en) * | 2021-02-25 | 2021-06-18 | 北京理工大学 | Confidence interval-based fault diagnosis method and system for lithium ion power battery pack |
| CN113459867A (en) * | 2021-07-19 | 2021-10-01 | 青岛科技大学 | Electric vehicle charging process fault early warning method based on adaptive deep confidence network |
| CN115327386A (en) * | 2022-08-09 | 2022-11-11 | 重庆大学 | Battery pack multi-fault diagnosis method based on electric-thermal coupling model |
| CN115792680A (en) * | 2022-12-26 | 2023-03-14 | 中山大学·深圳 | Retired battery health state assessment method based on Bayes deep learning |
| CN116482536A (en) * | 2023-01-30 | 2023-07-25 | 吉林大学 | Power battery fault early warning and safety risk assessment method based on data driving |
| CN116901707A (en) * | 2023-06-14 | 2023-10-20 | 浙江吉利控股集团有限公司 | Power battery pack fault early warning method, system and vehicle |
| CN117054887A (en) * | 2023-08-17 | 2023-11-14 | 摩形新能源汽车咨询集团(澄迈)有限公司 | Internal fault diagnosis method for lithium ion battery system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112092675B (en) | Battery thermal runaway early warning method, system and server | |
| Zhang et al. | Research on electric vehicle charging safety warning model based on back propagation neural network optimized by improved gray wolf algorithm | |
| Patil et al. | A novel multistage Support Vector Machine based approach for Li ion battery remaining useful life estimation | |
| CN112098850B (en) | Lithium ion battery voltage fault diagnosis method and system based on SDO algorithm | |
| CN111257753B (en) | Battery system fault diagnosis method | |
| CN112965001B (en) | Power battery pack fault diagnosis method based on real vehicle data | |
| Kamal et al. | Intelligent soft computing-based security control for energy management architecture of hybrid emergency power system for more-electric aircrafts | |
| CN115327386B (en) | Multi-fault diagnosis method for battery pack based on electrothermal coupling model | |
| CN117067920B (en) | Fault detection method and device of power battery, electronic equipment and electric automobile | |
| CN116400244B (en) | Abnormality detection method and device for energy storage battery | |
| CN117665590A (en) | Electrochemical energy storage power station battery fault early warning method and device based on multi-element multi-scale sample entropy | |
| Wang et al. | Research on interactive multi‐model fault diagnosis method of Li‐ion battery based on noise suppression | |
| CN116990689A (en) | Multi-feature correlation analysis intelligent lithium battery charger internal short circuit state evaluation method | |
| CN116125306A (en) | Power battery thermal runaway diagnosis method and system based on hybrid prediction framework | |
| Yang et al. | Multi-fault diagnosis for battery pack based on adaptive correlation sequence and sparse classification model | |
| CN117249921B (en) | Abnormality identification method for temperature sampling, related device, vehicle and storage medium | |
| CN117261599B (en) | Fault detection method and device of electric automobile, electronic equipment and electric automobile | |
| CN114460481A (en) | Energy storage battery thermal runaway early warning method based on Bi-LSTM and attention mechanism | |
| CN113935423A (en) | Power battery fault early warning method and system for coupling fuzzy control rule with Elman neural network | |
| CN116923188B (en) | Charging protection system of new energy vehicle | |
| Shen et al. | Concurrent multi-fault diagnosis of lithium-ion battery packs using random convolution kernel transformation and Gaussian process classifier | |
| Wang et al. | An inconsistency fault diagnosis method for lithium-ion cells in the battery pack based on piecewise dimensionality reduction and outlier identification | |
| CN117825957A (en) | Fault detection method of power battery | |
| CN112016597A (en) | Depth sampling method based on Bayesian imbalance measurement in machine learning | |
| US20220216700A1 (en) | Methods and systems for detecting faulty behavior in a battery |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |